Résumé
The rapid expansion of citizen science initiatives has led to a significant growth of biodiversitydatabases, and particularly presence-only (PO) observations. PO data are invaluable for understanding species distributions and their dynamics, but their use in a Species Distribution Model (SDM) is curtailed by sampling biases and the lack of information on absences. Poisson point processes are widely used for SDMs, with Maxent being one of the most popular methods. Maxent maximises the entropy of a probability distribution across sites as a function of predefined transformations of variables, called features. In contrast, neural networks and deep learning have emerged as a promising technique for automatic feature extraction from complex input variables. Arbitrarily complex transformations of input variables can be learned from the data efficiently through backpropagation and stochastic gradient descent (SGD). Yet, deep learning was mainly developed for classification problems, and learning robust features and species abundances across space while properly correcting for sampling biases has remained a challenge so far. In this paper, we propose DeepMaxent, which harnesses neural networks to automatically learn shared features among species, using the maximum entropy principle. To do so, it employs a normalised Poisson loss where for each species, presence probabilities across sites are modelled by a neural network. We evaluate DeepMaxent on a benchmark dataset known for its spatial sampling biases, using PO data for calibration and presence-absence (PA) data for validation across six regions with different biological groups and covariates. Our results indicate that DeepMaxent performs better than Maxent and other leading SDMs across all regions and taxonomic groups. The method performs particularly well in regions of uneven sampling, demonstrating substantial potential to increase SDM performances. The method opens the possibility to learn more robust features predicting simultaneously many species to arbitrary large datasets without increased memory requirements. The model likelihood, arising from a Poisson process, makes the method compatible with the integration of more standardised types of data to further increase sampling bias correction. In particular, our approach yields more accurate predictions than traditional single-species models, which opens up new possibilities for methodological enhancement.